You are helping the user convert a data file from one format to another using DuckDB.
Input file: $0
Output file: ${1:-}
Step 1 — Resolve input and output
Input: $0. If it's a bare filename (no /), resolve to a full path with find "$PWD" -name "$0" -not -path '*/.git/*' 2>/dev/null | head -1.
Output: If $1 is provided, use it as the output path. If not, default to the same stem as the input with a .parquet extension (e.g., data.csv → data.parquet).
Infer the output format from the output file extension:
| Extension |
Format clause |
.parquet, .pq |
(default, no clause needed) |
.csv |
(FORMAT csv, HEADER) |
.tsv |
(FORMAT csv, HEADER, DELIMITER '\t') |
.json |
(FORMAT json, ARRAY true) |
.jsonl, .ndjson |
(FORMAT json, ARRAY false) |
.xlsx |
(FORMAT xlsx) — requires INSTALL excel; LOAD excel; |
.geojson |
(FORMAT GDAL, DRIVER 'GeoJSON') — requires LOAD spatial; |
.gpkg |
(FORMAT GDAL, DRIVER 'GPKG') — requires LOAD spatial; |
.shp |
(FORMAT GDAL, DRIVER 'ESRI Shapefile') — requires LOAD spatial; |
Step 2 — Convert
Run a single DuckDB command. Prepend extension loads as needed based on both the input and output formats.
duckdb -c "
<EXTENSION_LOADS>
COPY (FROM '<INPUT_PATH>') TO '<OUTPUT_PATH>' <FORMAT_CLAUSE>;
"
For remote inputs (s3://, https://, etc.), prepend the same protocol setup as read-file:
| Protocol |
Prepend |
s3:// |
LOAD httpfs; CREATE SECRET (TYPE S3, PROVIDER credential_chain); |
gs:// / gcs:// |
LOAD httpfs; CREATE SECRET (TYPE GCS, PROVIDER credential_chain); |
https:// / http:// |
LOAD httpfs; |
If the user mentions partitioning (e.g., "partition by year"), add PARTITION_BY (col) to the format clause. This only works with Parquet and CSV output.
If the user mentions compression (e.g., "use zstd"), add CODEC 'zstd' for Parquet output.
Step 3 — Report
On success, report:
- Input file and detected format
- Output file, format, and size (
ls -lh)
- Row count if quick to compute
On failure:
duckdb: command not found → delegate to /duckdb-skills:install-duckdb- Missing extension → install it and retry
- Input parse error → suggest the user check the input format or try
/duckdb-skills:read-file first to inspect it
1---2name: convert-file3description: Convert any data file to another format: CSV, Parquet, JSON, Excel, GeoJSON, and more. Use when the user says "convert to parquet", "save as xlsx", "export as JSON", "make this a CSV", "turn into parquet", or any variation of format-to-format conversion for data files. Also triggers when the user wants to write Parquet, Excel, or other binary formats that Claude cannot produce natively.4---5
6You are helping the user convert a data file from one format to another using DuckDB.
7
8Input file: `$0`
9Output file: `${1:-}`
10
11## Step 1 — Resolve input and output
12
13**Input**: `$0`. If it's a bare filename (no `/`), resolve to a full path with `find "$PWD" -name "$0" -not -path '*/.git/*' 2>/dev/null | head -1`.
14
15**Output**: If `$1` is provided, use it as the output path. If not, default to the same stem as the input with a `.parquet` extension (e.g., `data.csv` → `data.parquet`).
16
17Infer the output format from the output file extension:
18
19| Extension | Format clause |
20|---|---|
21| `.parquet`, `.pq` | *(default, no clause needed)* |
22| `.csv` | `(FORMAT csv, HEADER)` |
23| `.tsv` | `(FORMAT csv, HEADER, DELIMITER '\t')` |
24| `.json` | `(FORMAT json, ARRAY true)` |
25| `.jsonl`, `.ndjson` | `(FORMAT json, ARRAY false)` |
26| `.xlsx` | `(FORMAT xlsx)` — requires `INSTALL excel; LOAD excel;` |
27| `.geojson` | `(FORMAT GDAL, DRIVER 'GeoJSON')` — requires `LOAD spatial;` |
28| `.gpkg` | `(FORMAT GDAL, DRIVER 'GPKG')` — requires `LOAD spatial;` |
29| `.shp` | `(FORMAT GDAL, DRIVER 'ESRI Shapefile')` — requires `LOAD spatial;` |
30
31## Step 2 — Convert
32
33Run a single DuckDB command. Prepend extension loads as needed based on both the input and output formats.
34
35```bash
36duckdb -c "
37<EXTENSION_LOADS>
38COPY (FROM '<INPUT_PATH>') TO '<OUTPUT_PATH>' <FORMAT_CLAUSE>;
39"
40```
41
42For remote inputs (`s3://`, `https://`, etc.), prepend the same protocol setup as `read-file`:
43
44| Protocol | Prepend |
45|---|---|
46| `s3://` | `LOAD httpfs; CREATE SECRET (TYPE S3, PROVIDER credential_chain);` |
47| `gs://` / `gcs://` | `LOAD httpfs; CREATE SECRET (TYPE GCS, PROVIDER credential_chain);` |
48| `https://` / `http://` | `LOAD httpfs;` |
49
50**If the user mentions partitioning** (e.g., "partition by year"), add `PARTITION_BY (col)` to the format clause. This only works with Parquet and CSV output.
51
52**If the user mentions compression** (e.g., "use zstd"), add `CODEC 'zstd'` for Parquet output.
53
54## Step 3 — Report
55
56On success, report:
57- Input file and detected format
58- Output file, format, and size (`ls -lh`)
59- Row count if quick to compute
60
61On failure:
62- **`duckdb: command not found`** → delegate to `/duckdb-skills:install-duckdb`
63- **Missing extension** → install it and retry
64- **Input parse error** → suggest the user check the input format or try `/duckdb-skills:read-file` first to inspect it
duckdb